相关论文: Language Transfer of Audio Word2Vec: Learning Audi…

Voice Conversion (VC) modifies speech to match a target speaker while preserving linguistic content. Traditional methods usually extract speaker information directly from speech while neglecting the explicit utilization of linguistic…

Speech is the most natural way of expressing ourselves as humans. Identifying emotion from speech is a nontrivial task due to the ambiguous definition of emotion itself. Speaker Emotion Recognition (SER) is essential for understanding human…

It is challenging to extract semantic meanings directly from audio signals in spoken language understanding (SLU), due to the lack of textual information. Popular end-to-end (E2E) SLU models utilize sequence-to-sequence automatic speech…

Wav2vec 2.0 is a recently proposed self-supervised framework for speech representation learning. It follows a two-stage training process of pre-training and fine-tuning, and performs well in speech recognition tasks especially ultra-low…

Autoregressive language models are powerful and relatively easy to train. However, these models are usually trained without explicit conditioning labels and do not offer easy ways to control global aspects such as sentiment or topic during…

Recently, end-to-end (E2E) models become a competitive alternative to the conventional hybrid automatic speech recognition (ASR) systems. However, they still suffer from speaker mismatch in training and testing condition. In this paper, we…

All-neural end-to-end (E2E) automatic speech recognition (ASR) systems that use a single neural network to transduce audio to word sequences have been shown to achieve state-of-the-art results on several tasks. In this work, we examine the…

Generating spoken word embeddings that possess semantic information is a fascinating topic. Compared with text-based embeddings, they cover both phonetic and semantic characteristics, which can provide richer information and are potentially…

Neural latent variable models enable the discovery of interesting structure in speech audio data. This paper presents a comparison of two different approaches which are broadly based on predicting future time-steps or auto-encoding the…

Text word embeddings that encode distributional semantics work by modeling contextual similarities of frequently occurring words. Acoustic word embeddings, on the other hand, typically encode low-level phonetic similarities. Semantic…

Deep speaker embedding has achieved satisfactory performance in speaker verification. By enforcing the neural model to discriminate the speakers in the training set, deep speaker embedding (called `x-vectors`) can be derived from the hidden…

The goal of Audio-Visual Segmentation (AVS) is to localize and segment the sounding source objects from video frames. Research on AVS suffers from data scarcity due to the high cost of fine-grained manual annotations. Recent works attempt…

Natural language processing techniques, such as Word2Vec, have demonstrated exceptional capabilities in capturing semantic and syntactic relationships of text through vector embeddings. Inspired by this technique, we propose CSI2Vec, a…

End-to-end speech recognition is a promising technology for enabling compact automatic speech recognition (ASR) systems since it can unify the acoustic and language model into a single neural network. However, as a drawback, training of…

This paper introduces FastVC, an end-to-end model for fast Voice Conversion (VC). The proposed model can convert speech of arbitrary length from multiple source speakers to multiple target speakers. FastVC is based on a conditional…

Though significant progress has been made for the voice conversion (VC) of typical speech, VC for atypical speech, e.g., dysarthric and second-language (L2) speech, remains a challenge, since it involves correcting for atypical prosody…

We describe a neural network-based system for text-to-speech (TTS) synthesis that is able to generate speech audio in the voice of many different speakers, including those unseen during training. Our system consists of three independently…

This paper explores applying the wav2vec2 framework to speaker recognition instead of speech recognition. We study the effectiveness of the pre-trained weights on the speaker recognition task, and how to pool the wav2vec2 output sequence…

Current simultaneous speech translation models can process audio only up to a few seconds long. Contemporary datasets provide an oracle segmentation into sentences based on human-annotated transcripts and translations. However, the…

Lipreading is an important technique for facilitating human-computer interaction in noisy environments. Our previously developed self-supervised learning method, AV2vec, which leverages multimodal self-distillation, has demonstrated…